© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34272
    Prev
    Next
    INDEX
    Explanations

    Belgium

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     K
    0.46
     Brussels
    0.44
    Brussels
    0.40
    тку
    0.39
     Bruxelles
    0.38
     প্রত্যাবর্তন
    0.38
     V
    0.37
     Belg
    0.36
     VD
    0.36
     skirts
    0.36
    POSITIVE LOGITS
     Sicher
    0.41
    Sto
    0.39
    َّا
    0.38
    பதி
    0.38
    xcschemes
    0.38
     ಶೆ
    0.38
     Sto
    0.38
     vol
    0.37
    aisse
    0.37
    '],$
    0.37
    Activations Density 0.002%

    No Known Activations